Addition of AI to Mammogram Screenings Bolsters Cancer Detection Rates

CancerNetwork® spoke with Arturo Loaiza-Bonilla, MD, MSEd, FACP, systemwide chief of Hematology and Oncology at Saint Luke’s University Health Network (SLUHN), about notable ongoing clinical trials evaluating the application of artificial intelligence (AI) into clinical practice.

Loaiza-Bonilla began by expressing that many AI tools have received FDA clearance but have not undergone any real-world testing. He emphasized that despite the importance of making solutions widely available to the public, a cross comparison involving the use of an AI tool, the use of an AI tool in tandem with a clinician, and clinician input alone are essential to test the efficacy of an intervention.

Highlighting results from the randomized Mammography Screening in Artificial Intelligence (MASAI) trial (NCT04838756) published in The Lancet, he stated that AI-assisted mammograms were able to detect cancers with optimized recall compared with standard mammograms.¹ Loaiza-Bonilla then suggested that the findings from this study have led to a recently announced UK-based clinical study, the Early Detection using Information Technology (EDITH) trial, which is purported to be one of the largest prospective evaluations of AI-assisted mammography.² The details of the study have not been released, but a news release outlined that the study investigators will plan to enroll approximately 700,000 women while utilizing 5 AI platforms across 30 National Health Service (NHS) sites. Researchers are receiving £11 million from the UK government to conduct this study.

Transcript:

One of the things that has been emerging from [AI’s growth] is that many of these tools are released as FDA-approved, [and] you may want to test [them], but many of them have not been compared to reality. Many of the solutions can be important, but we need to have cross comparison with what happens when we have the AI tool vs the AI tool plus the clinician vs the clinician alone. The first few studies that have come up, at least with some results that I am interested [in], are on the diagnostic side.

A few days ago, we heard from this randomized clinical trial, called the MASAI trial, [which] was published in The Lancet. It showed that mammograms, digitally assisted by AI, were able to detect with optimized recalls compared to the readings on their own, making them more efficient. That is now leading, for example, to another study that is about to launch in the UK called the Early Detection using Information Technology in Health [EDITH] trial. We still do not have the full details, but it was supposedly announced by the UK Government. [It will be] one of the largest AI prospective evaluations in mammography. They will plan to enroll [700,000] women in 5 AI platforms––not just 1 AI platform, but 5––across 30 NHS sites. The government is giving [£11 million] to fund this.

This is all based on the MASAI trial from Sweden, which is the precursor study to this, that shows that AI increased cancer detection by mammogram by 29% compared to standard screening and reduced the interval cancers by 19% at 2-year follow up. [Quite] promising, showing a non-inferiority to double reading in AI, maintaining a rate of [6.4] cancers per 1000 screens, vs [5.0] manually. I know you [may] say, “Oh, [it is only 1.4%],” but if you compound that by the hundreds of 1000s of mammograms we do, that helps [many] patients. I am interested [in following] those studies.

References

1. Hernström V, Josefsson V, Sartor H, et al. Screening performance and characteristics of breast cancer detected in the Mammography Screening with Artificial Intelligence trial (MASAI): a randomised, controlled, parallel-group, non-inferiority, single-blinded, screening accuracy study. The Lancet. Published online February 3, 2025. doi:10.1016/ S2589-7500(24)00267-X
2. World-leading AI trial to tackle breast cancer launched. News release. Gov.UK. February 4, 2025. https://tinyurl.com/3hna99we